57e90d0f83
Add Codex marketplace metadata and a repo-local plugin scaffold so the repository can be installed as a Codex plugin without duplicating the skills catalog. Document the new integration path and cover it with a regression test to keep the marketplace entry and plugin manifest in sync.
2.7 KiB
2.7 KiB
Codex CLI Skills
If you want Codex CLI skills that are easy to install and practical in a local coding loop, this repository is designed for that exact use case.
Antigravity Awesome Skills supports Codex CLI through the .codex/skills/ path and gives you a wide set of reusable task playbooks for planning, implementation, debugging, testing, security review, and delivery.
How to use Antigravity Awesome Skills with Codex CLI
Install the library into your Codex path, then invoke focused skills directly in your prompt. The most common pattern is:
- install with
npx antigravity-awesome-skills --codex - choose one workflow-oriented skill such as
@brainstorming,@concise-planning, or@test-driven-development - ask Codex to apply that skill to a concrete file, feature, test, or bugfix
Why use this repo for Codex CLI
- It supports Codex CLI with a dedicated install flag and a standard skills layout.
- It is strong for local repo work where you want to move from planning to implementation to verification without changing libraries.
- It includes both general-purpose engineering skills and deeper specialist tracks.
- It gives you docs and bundles, not just raw skill files.
Install Codex CLI Skills
npx antigravity-awesome-skills --codex
If you prefer a plugin-style Codex integration, this repository also ships repo-local plugin metadata in .agents/plugins/marketplace.json and plugins/antigravity-awesome-skills/.codex-plugin/plugin.json.
Verify the install
test -d .codex/skills || test -d ~/.codex/skills
Best starter skills for Codex CLI
brainstorming: clarify requirements before touching code.concise-planning: turn ambiguous work into an atomic execution plan.test-driven-development: structure changes around red-green-refactor.lint-and-validate: keep quality checks close to the implementation loop.create-pr: wrap up work cleanly once implementation is done.
Example Codex CLI prompts
Use @concise-planning to break this feature request into an implementation checklist.
Use @test-driven-development to add tests before changing this parser.
Use @create-pr once everything is passing and summarize the user-facing changes.
What to do next
- Read
ai-agent-skills.mdif you want a framework for choosing between broad and curated skill libraries. - Use
workflows.mdwhen you want step-by-step execution patterns for common engineering goals. - Return to
README.mdfor the full compatibility matrix.